Training in progress, step 67, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2176b14231c3eb02c10012ad86d2341b786680f2ed895ff8114d3fabb5d908
+oid sha256:fbc903b225254205d5609fc06d6a8bfa90c2744f381f1b54c484b7a621b60654
 size 3029024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de81114122a4b83d977f69d642b99107558fbd31c4c055312847628945564707
+oid sha256:f89f509063c99594509fc0d881ffc152e6745110b5e6eccc9926de8f3d0c23de
 size 1663290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9926377e14a32bcf24c41ab954e7bbaa5f5c82b837a097a1f57d63fc76b0a72d
+oid sha256:cbbf69c8ecb2a30450d6e4adaa16b4c744e511c98459f16c0df68527f34240b2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2c525a78bb0d857c1f56051d584b3d76436759527cfb06c70ff3eda3c53e6c
+oid sha256:e96cf9993f0a7ece18ff2a2f23e1a5ef16397f127608e0f7b060a528f71e904f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0861cf310ecbf6935262d62bb50cfccf12d1e5ef4db8bb53e8b7f3a5b8ef4948
+oid sha256:a96ecd88860bbc6228ac216161b67a4d387680109fa473789c40e22b22390bc0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e311e8e9447f869a5b7ca0c8446ed2e4d677d99e4aa15edb9884ea383899628
+oid sha256:b0bce2d178653c62c8ff46e4bd12edb3b0b62580bb9194ecd3b372bb0081df37
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9658935ff11be9df8b51b7d8b86085c64d449c3c13854fc482d6b9c48fbbd70c
+oid sha256:e62d59ca1562da87bb62e6afbbddb7b7268189064dc1b187dce39757c401c47c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.433828830718994,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.246498599439776,
+  "epoch": 3.011204481792717,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 67,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,125 @@
       "eval_samples_per_second": 254.153,
       "eval_steps_per_second": 16.096,
       "step": 50
+    },
+    {
+      "epoch": 2.291316526610644,
+      "grad_norm": 1.2064857482910156,
+      "learning_rate": 2.5970912240665813e-05,
+      "loss": 2.4134,
+      "step": 51
+    },
+    {
+      "epoch": 2.3361344537815127,
+      "grad_norm": 1.254510760307312,
+      "learning_rate": 2.3095882341831372e-05,
+      "loss": 2.4845,
+      "step": 52
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 1.4852594137191772,
+      "learning_rate": 2.0341012763532243e-05,
+      "loss": 2.4392,
+      "step": 53
+    },
+    {
+      "epoch": 2.425770308123249,
+      "grad_norm": 0.9326648116111755,
+      "learning_rate": 1.771860742205988e-05,
+      "loss": 2.422,
+      "step": 54
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 1.0687801837921143,
+      "learning_rate": 1.5240378616267886e-05,
+      "loss": 2.3847,
+      "step": 55
+    },
+    {
+      "epoch": 2.515406162464986,
+      "grad_norm": 0.8696810007095337,
+      "learning_rate": 1.2917394717602121e-05,
+      "loss": 2.3407,
+      "step": 56
+    },
+    {
+      "epoch": 2.560224089635854,
+      "grad_norm": 1.5607281923294067,
+      "learning_rate": 1.0760030736066951e-05,
+      "loss": 2.9372,
+      "step": 57
+    },
+    {
+      "epoch": 2.6050420168067228,
+      "grad_norm": 1.2624620199203491,
+      "learning_rate": 8.777921982911996e-06,
+      "loss": 2.5201,
+      "step": 58
+    },
+    {
+      "epoch": 2.649859943977591,
+      "grad_norm": 1.4880586862564087,
+      "learning_rate": 6.979921036993042e-06,
+      "loss": 2.9394,
+      "step": 59
+    },
+    {
+      "epoch": 2.6946778711484596,
+      "grad_norm": 0.8246588706970215,
+      "learning_rate": 5.374058207005944e-06,
+      "loss": 2.3346,
+      "step": 60
+    },
+    {
+      "epoch": 2.7394957983193278,
+      "grad_norm": 1.5645203590393066,
+      "learning_rate": 3.967505666178556e-06,
+      "loss": 2.7406,
+      "step": 61
+    },
+    {
+      "epoch": 2.784313725490196,
+      "grad_norm": 1.2056126594543457,
+      "learning_rate": 2.7665454196040664e-06,
+      "loss": 2.396,
+      "step": 62
+    },
+    {
+      "epoch": 2.8291316526610646,
+      "grad_norm": 2.0966439247131348,
+      "learning_rate": 1.7765412472811771e-06,
+      "loss": 3.1009,
+      "step": 63
+    },
+    {
+      "epoch": 2.8739495798319328,
+      "grad_norm": 0.9577468633651733,
+      "learning_rate": 1.0019147481706625e-06,
+      "loss": 2.4537,
+      "step": 64
+    },
+    {
+      "epoch": 2.918767507002801,
+      "grad_norm": 1.0243852138519287,
+      "learning_rate": 4.461255922609986e-07,
+      "loss": 2.4703,
+      "step": 65
+    },
+    {
+      "epoch": 2.9635854341736696,
+      "grad_norm": 1.1177788972854614,
+      "learning_rate": 1.1165606884234181e-07,
+      "loss": 2.6208,
+      "step": 66
+    },
+    {
+      "epoch": 3.011204481792717,
+      "grad_norm": 3.6235415935516357,
+      "learning_rate": 0.0,
+      "loss": 4.9354,
+      "step": 67
     }
   ],
   "logging_steps": 1,
@@ -396,12 +515,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 523298144256000.0,
+  "total_flos": 701219513303040.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null